Multidestination Message Passing Mechanism Conforming to Base Wormhole Routing Scheme

A new concept of multidestination wormhole mechanism is proposed which allows a message to be propagated along any valid path in a wormhole network conforming to the underlying base routing scheme (ecube, planar, turn, or fully adaptive). Two schemes are developed and evaluated to perform fast multicasting and broadcasting in 2D/3D meshes/tori using this new mechanism. Not only do these schemes demonstrate superiority over Umesh [10] and Hamiltonian Path [9] schemes, they indicate an interesting result that the cost of multicast can be reduced or kept near-constant as the degree of multicast increases. Variations of the proposed schemes to take advantage of routing-adaptivity are also presented. These results are the first ones in the wormhole-routing literature to propose multicasting schemes with such reduced overhead and provision for taking advantage of adaptivity. It lays a new foundation in building high-performance wormhole architecture for supporting fast collective communication operations.

[1]  Dhabaleswar K. Panda.  Optimal Phase Barrier Synchronization in K-ary N-cube Wormhole-routed Systems Using Multirendezvous Primitives , 1993 .

[2]  Xiaola Lin,et al.  Adaptive wormhole routing in hypercube multicomputers , 1993, Proceedings of 1993 5th IEEE Symposium on Parallel and Distributed Processing.

[3]  Debashis Basak,et al.  Scalable architectures with k-ary n-cube cluster-c organization , 1993, Proceedings of 1993 5th IEEE Symposium on Parallel and Distributed Processing.

[4]  Robert A. van de Geijn,et al.  Optimal Broadcasting in Mesh-Connected Architectures , 1991 .

[5]  D. S. Scott.  All-to-All Communication Patterns in Hypercubes and Mesh Topologies , 1991 .

[6]  D. S. Scott,et al.  Efficient All-to-All Communication Patterns in Hypercube and Mesh Topologies , 1991, The Sixth Distributed Memory Computing Conference, 1991. Proceedings.

[7]  D.K. Panda,et al.  Message-ordering for wormhole-routed multiport systems with link contention and routing adaptivity , 1994, Proceedings of IEEE Scalable High Performance Computing Conference.

[8]  Andrew A. Chien,et al.  Planar-adaptive routing: low-cost adaptive networks for multiprocessors , 1992, ISCA '92.

[9]  Lionel M. Ni,et al.  Multi-address Encoding for Multicast , 1994, PCRCW.

[10]  Dhabaleswar K. Panda,et al.  Barrier synchronization in distributed-memory multiprocessors using rendezvous primitives , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[11]  Anoop Gupta,et al.  The Stanford Dash multiprocessor , 1992, Computer.

[12]  Xiaola Lin,et al.  Deadlock-free multicast wormhole routing in multicomputer networks , 1991, ISCA '91.

[13]  Jehoshua Bruck,et al.  Multiple message broadcasting with generalized Fibonacci trees , 1992, [1992] Proceedings of the Fourth IEEE Symposium on Parallel and Distributed Processing.

[14]  B. Duzett,et al.  An overview of the nCUBE 3 supercomputer , 1992, [Proceedings 1992] The Fourth Symposium on the Frontiers of Massively Parallel Computation.

[15]  Lionel M. Ni,et al.  A survey of wormhole routing techniques in direct networks , 1993, Computer.

[16]  Message Passing Interface Forum.  MPI: A message - passing interface standard , 1994 .

[17]  Cauligi S. Raghavendra,et al.  On multicast wormhole routing in multicomputer networks , 1994, Proceedings of 1994 6th IEEE Symposium on Parallel and Distributed Processing.

[18]  William J. Dally,et al.  Deadlock-Free Message Routing in Multiprocessor Interconnection Networks , 1987, IEEE Transactions on Computers.

[19]  Hong Xu,et al.  Efficient implementation of barrier synchronization in wormhole-routed hypercube multicomputers , 1992, [1992] Proceedings of the 12th International Conference on Distributed Computing Systems.

[20]  José Duato,et al.  A new theory of deadlock-free adaptive multicast routing in wormhole networks , 1993, Proceedings of 1993 5th IEEE Symposium on Parallel and Distributed Processing.

[21]  Shahid H. Bokhari,et al.  Complete exchange on a circuit switched mesh , 1992, Proceedings Scalable High Performance Computing Conference SHPCC-92..

[22]  Dhabaleswar K. Panda,et al.  Impact of multiple consumption channels on wormhole routed k-ary n-cube networks , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[23]  Mary K. Vernon,et al.  Performance Analysis of Mesh Interconnection Networks with Deterministic Routing , 1994, IEEE Trans. Parallel Distributed Syst..

[24]  José Duato,et al.  A New Theory of Deadlock-Free Adaptive Routing in Wormhole Networks , 1993, IEEE Trans. Parallel Distributed Syst..

[25]  Herb Schwetman,et al.  Using CSIM to model complex systems , 1988, 1988 Winter Simulation Conference Proceedings.

[26]  G.D. Pifarre,et al.  Fully Adaptive Minimal Deadlock-Free Packet Routing in Hypercubes, Meshes, and other Networks: Algorithms and Simulations , 1994, IEEE Trans. Parallel Distributed Syst..

[27]  Xiaola Lin,et al.  Performance Evaluation of Multicast Wormhole Routing in 2D-Mesh Multicomputers , 1991, ICPP.

[28]  S. Lennart Johnsson,et al.  Optimum Broadcasting and Personalized Communication in Hypercubes , 1989, IEEE Trans. Computers.

[29]  Amotz Bar-Noy,et al.  Multiple message broadcasting in the postal model , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[30]  Hong Xu,et al.  Unicast-Based Multicast Communication in Wormhole-Routed Networks , 1994, IEEE Trans. Parallel Distributed Syst..

[31]  Suresh Chalasani,et al.  A comparison of adaptive wormhole routing algorithms , 1993, ISCA '93.